Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5767 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.8857. Min Act: -0.1700
Data Index: 8608772 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.8544. Min Act: -0.1700
Data Index: 108481 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.7607. Min Act: -0.1700
Data Index: 4856549 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.7607. Min Act: -0.1700
Data Index: 791574 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.7607. Min Act: -0.1700
Data Index: 4812457 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.6357. Min Act: -0.1700
Data Index: 2523398 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.6044. Min Act: -0.1700
Data Index: 5166716 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.5732. Min Act: -0.1700
Data Index: 8117980 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.5732. Min Act: -0.1700
Data Index: 3267475 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.5419. Min Act: -0.1700
Data Index: 7115182 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.5107. Min Act: -0.1700
Data Index: 4422176 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.5107. Min Act: -0.1700
Data Index: 3539912 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4794. Min Act: -0.1700
Data Index: 4925272 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4482. Min Act: -0.1700
Data Index: 6627226 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.3857. Min Act: -0.1700
Data Index: 34988 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4169. Min Act: -0.1700
Data Index: 8289668 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4169. Min Act: -0.1700
Data Index: 8206207 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4482. Min Act: -0.1700
Data Index: 8826159 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4169. Min Act: -0.1700
Data Index: 3946742 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8857. Min Range: -4.8857
Max Act: 4.4169. Min Act: -0.1700
Data Index: 3486906 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19